Authors : Rajesh Chauhan; Satish Gupta; Ayush Khanal; Anand Maha

Volume/Issue : Volume 11 - 2026, Issue 4 - April

Google Scholar : https://tinyurl.com/yc3w6rv6

Scribd : https://tinyurl.com/m9mtr58c

DOI : https://doi.org/10.38124/ijisrt/26apr1874

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : The rapid growth of digital communication platforms has led to a significant increase in online scams, phishing attacks, and AI-generated deepfake content, posing serious risks to individuals and organizations. Existing security solutions are often fragmented, addressing only a single threat type and lacking real-time, user-centric analysis. To overcome these limitations, this paper presents SafeNet.AI, a unified, AI-powered web platform designed to detect phishing URLs, scam messages, and manipulated media content within a single framework. The proposed system integrates machine learning models for URL-based fraud detection, natural language processing techniques for scam text classification, and deep learning-based computer vision models for deepfake detection. The platform is deployed as a scalable web application, providing real-time analysis, risk assessment, and user-friendly visualization of results. Experimental evaluation based on standard datasets demonstrates that SafeNet.AI achieves reliable detection performance across multiple threat categories, highlighting its potential as an effective and practical solution for enhancing digital security.

Keywords : Cybersecurity, Phishing Detection, Scam Text Classification, Deepfake Detection, Artificial Intelligence, Machine Learning, Web-Based Security Platform.

References :

1. R. Basnet, A. H. Sung, and Q. Liu, “Feature-based phishing detection,” Int. J. Comput. Commun. Control, vol. 7, no. 4, pp. 1–10, 2012.
2. T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” in Proc. 22nd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, 2016, pp. 785–794.
3. J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of deep bidirectional transformers for language understanding,” in Proc. NAACL-HLT, 2019, pp. 4171–4186.
4. F. Matern, C. Riess, and M. Stamminger, “Exploiting visual artifacts to expose deepfakes and face manipulations,” in Proc. IEEE WACVW, 2019, pp. 83–92.
5. A. Rössler et al., “FaceForensics++: Learning to detect manipulated facial images,” in Proc. IEEE/CVF Int. Conf. Computer Vision (ICCV), 2019, pp. 1–11.
6. A. Vaswani et al., “Attention is all you need,” in Advances in Neural Information Processing Systems (NeurIPS), 2017, pp. 5998–6008.
7. Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, pp. 436–444, 2015.
8. K. R. Choo, “The cyber threat landscape: Challenges and future research directions,” Computers & Security, vol. 30, no. 8, pp. 719–731, 2011.
9. Google, “Safe Browsing API: Protecting users from dangerous sites,” Google Security Whitepaper, 2023.
10. N. Carlini et al., “On evaluating adversarial robustness,” in Proc. IEEE Symp. Security and Privacy, 2019, pp. 39–57.